Fusão de dados multisensor para a identificação e o mapeamento de ambientes flúvio-estuarinos da Amazônia

A fusão de imagens multisensor tem sido um procedimento amplamente utilizado em função da natureza complementar dos vários conjuntos de dados. Este artigo compara o desempenho de quatro métodos diferentes para fusão de imagens Landsat-7 ETM+ e RADARSAT-1 W1. A comparação foi baseada nas características espectrais das imagens, utilizando-se de análise estatística e visual dos produtos gerados. Quatro métodos foram usados para a fusão das imagens Landsat-7 ETM+ e RADARSAT-1 W1: i) fusão do SAR (radar de abertura sintética) com a tríade selecionada pelo OIF (Optimum Index Factor); ii) realce por decorrelação da tríade selecionada pelo OIF, seguida da fusão com SAR; iii) ACP (Análise por Componentes Principais) para as seis bandas ETM+ do espectro refletido (1, 2, 3, 4, 5 e 7) e posterior fusão das três primeiras componentes principais (1CP; 2CP; 3CP) com o SAR; iv) SPC-SAR (Principal Componente Seletivo - SAR). O produto SPC-SAR mostrou melhor desempenho na identificação das feições costeiras e permitiu o realce mais efetivo dos diferentes ambientes.

Geoestatística multivariada na delimitação de zonas de manejo na cultura de cana-de-açúcar

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Leitor contemporâneo: os livros mais vendidos no Brasil de 1966 a 2004

Este trabalho procura examinar o que o leitor brasileiro contemporâneo lê, com o propósito de explicar as razões que levam esse leitor a realizar suas escolhas. Nesse sentido, portanto, o objetivo central do trabalho será examinar o perfil desse leitor brasileiro. O levantamento dos dados para estabelecer o corpus da pesquisa foi realizado por meio do registro das listas de livros mais vendidos, publicadas em dois jornais brasileiros. O primeiro jornal fonte da pesquisa foi o Leia, periódico mensal que circulou no território nacional durante o período de abril de 1978 a setembro de 1991. O segundo, foi o Jornal do Brasil, diário carioca que publicou listas dos livros mais vendidos no Brasil a partir de 1966 até o mês de dezembro de 2004, data de encerramento da pesquisa, em caderno destinado à leitura. Como o segundo jornal interrompeu a publicação das listas dos mais vendidos durante o período de fevereiro de 1976 a abril de 1984, propusemos uma fusão dos dados dos dois jornais de forma a cobrir um período que compreende os anos de 1966 até 2004. A base teórica a partir da qual se estabeleceu o exame do perfil do leitor brasileiro foi a semiótica da escola de Paris. Para o tratamento da questão da leitura elegeu-se o exame das manifestações da enunciação no discurso, as projeções do enunciador e do enunciatário e o tratamento das paixões. Foram observados em cada um dos textos do corpus como essas categorias enunciativas projetam-se em cada um dos textos mais lidos pelos leitores brasileiros e, posteriormente, como, nas listas dos livros mais vendidos, esse leitor manifesta-se como enunciador. Para tanto propôs-se a contraposição entre o ethos do enunciador-leitor das listas e o pathos do enunciatário dos discursos de leitura. Uma vez que o corpus da pesquisa revelou um crescimento na opção pelos textos de auto-ajuda, foi examinada a questão específica... (Resumo completo, clicar acesso eletrônico abaixo)

Progetto di reti Sensori Wireless e tecniche di Fusione Sensoriale

Ambient Intelligence (AmI) envisions a world where smart, electronic environments are aware and responsive to their context. People moving into these settings engage many computational devices and systems simultaneously even if they are not aware of their presence. AmI stems from the convergence of three key technologies: ubiquitous computing, ubiquitous communication and natural interfaces. The dependence on a large amount of fixed and mobile sensors embedded into the environment makes of Wireless Sensor Networks one of the most relevant enabling technologies for AmI. WSN are complex systems made up of a number of sensor nodes, simple devices that typically embed a low power computational unit (microcontrollers, FPGAs etc.), a wireless communication unit, one or more sensors and a some form of energy supply (either batteries or energy scavenger modules). Low-cost, low-computational power, low energy consumption and small size are characteristics that must be taken into consideration when designing and dealing with WSNs. In order to handle the large amount of data generated by a WSN several multi sensor data fusion techniques have been developed. The aim of multisensor data fusion is to combine data to achieve better accuracy and inferences than could be achieved by the use of a single sensor alone. In this dissertation we present our results in building several AmI applications suitable for a WSN implementation. The work can be divided into two main areas: Multimodal Surveillance and Activity Recognition. Novel techniques to handle data from a network of low-cost, low-power Pyroelectric InfraRed (PIR) sensors are presented. Such techniques allow the detection of the number of people moving in the environment, their direction of movement and their position. We discuss how a mesh of PIR sensors can be integrated with a video surveillance system to increase its performance in people tracking. Furthermore we embed a PIR sensor within the design of a Wireless Video Sensor Node (WVSN) to extend its lifetime. Activity recognition is a fundamental block in natural interfaces. A challenging objective is to design an activity recognition system that is able to exploit a redundant but unreliable WSN. We present our activity in building a novel activity recognition architecture for such a dynamic system. The architecture has a hierarchical structure where simple nodes performs gesture classification and a high level meta classifiers fuses a changing number of classifier outputs. We demonstrate the benefit of such architecture in terms of increased recognition performance, and fault and noise robustness. Furthermore we show how we can extend network lifetime by performing a performance-power trade-off. Smart objects can enhance user experience within smart environments. We present our work in extending the capabilities of the Smart Micrel Cube (SMCube), a smart object used as tangible interface within a tangible computing framework, through the development of a gesture recognition algorithm suitable for this limited computational power device. Finally the development of activity recognition techniques can greatly benefit from the availability of shared dataset. We report our experience in building a dataset for activity recognition. Such dataset is freely available to the scientific community for research purposes and can be used as a testbench for developing, testing and comparing different activity recognition techniques.

A user supported object tracking framework for interactive video production

We present a user supported tracking framework that combines automatic tracking with extended user input to create error free tracking results that are suitable for interactive video production. The goal of our approach is to keep the necessary user input as small as possible. In our framework, the user can select between different tracking algorithms - existing ones and new ones that are described in this paper. Furthermore, the user can automatically fuse the results of different tracking algorithms with our robust fusion approach. The tracked object can be marked in more than one frame, which can significantly improve the tracking result. After tracking, the user can validate the results in an easy way, thanks to the support of a powerful interpolation technique. The tracking results are iteratively improved until the complete track has been found. After the iterative editing process the tracking result of each object is stored in an interactive video file that can be loaded by our player for interactive videos.

Unsupervised method to classify PM10 pollutant concentrations

In this paper a method based mainly on Data Fusion and Artificial Neural Networks to classify one of the most important pollutants such as Particulate Matter less than 10 micrometer in diameter (PM10) concentrations is proposed. The main objective is to classify in two pollution levels (Non-Contingency and Contingency) the pollutant concentration. Pollutant concentrations and meteorological variables have been considered in order to build a Representative Vector (RV) of pollution. RV is used to train an Artificial Neural Network in order to classify pollutant events determined by meteorological variables. In the experiments, real time series gathered from the Automatic Environmental Monitoring Network (AEMN) in Salamanca Guanajuato Mexico have been used. The method can help to establish a better air quality monitoring methodology that is essential for assessing the effectiveness of imposed pollution controls, strategies, and facilitate the pollutants reduction.

Arranjos de sensores orientados à missão para a geração automática de mapas temáticos em VANTs

O uso de veículos aéreos não tripulados (VANTs) tem se tornado cada vez mais comum, principalmente em aplicações de uso civil. No cenário militar, o uso de VANTs tem focado o cumprimento de missões específicas que podem ser divididas em duas grandes categorias: sensoriamento remoto e transporte de material de emprego militar. Este trabalho se concentra na categoria do sensoriamento remoto. O trabalho foca a definição de um modelo e uma arquitetura de referência para o desenvolvimento de sensores inteligentes orientados a missões específicas. O principal objetivo destas missões é a geração de mapas temáticos. Neste trabalho são investigados processos e mecanismos que possibilitem a geração desta categoria de mapas. Neste sentido, o conceito de MOSA (Mission Oriented Sensor Array) é proposto e modelado. Como estudos de caso dos conceitos apresentados são propostos dois sistemas de mapeamento automático de fontes sonoras, um para o caso civil e outro para o caso militar. Essas fontes podem ter origem no ruído gerado por grandes animais (inclusive humanos), por motores de combustão interna de veículos ou por atividade de artilharia (incluindo caçadores). Os MOSAs modelados para esta aplicação são baseados na integração de dados provenientes de um sensor de imageamento termal e uma rede de sensores acústicos em solo. A integração das informações de posicionamento providas pelos sensores utilizados, em uma base cartográfica única, é um dos aspectos importantes tratados neste trabalho. As principais contribuições do trabalho são a proposta de sistemas MOSA, incluindo conceitos, modelos, arquitetura e a implementação de referência representada pelo sistema de mapeamento automático de fontes sonoras.

Closed-Loop Deep Brain Stimulation: Bidirectional Neuroprosthetics for Tremor and BCI

Thesis (Ph.D.)--University of Washington, 2016-06

Automatic building detection using the Dempster-Shafer algorithm

An approach and strategy for automatic detection of buildings from aerial images using combined image analysis and interpretation techniques is described in this paper. It is undertaken in several steps. A dense DSM is obtained by stereo image matching and then the results of multi-band classification, the DSM, and Normalized Difference Vegetation Index (NDVI) are used to reveal preliminary building interest areas. From these areas, a shape modeling algorithm has been used to precisely delineate their boundaries. The Dempster-Shafer data fusion technique is then applied to detect buildings from the combination of three data sources by a statistically-based classification. A number of test areas, which include buildings of different sizes, shape, and roof color have been investigated. The tests are encouraging and demonstrate that all processes in this system are important for effective building detection.

Multisensorial obstacles detection and classification for ADAS and autonomous driving

A reliable perception of the real world is a key-feature for an autonomous vehicle and the Advanced Driver Assistance Systems (ADAS). Obstacles detection (OD) is one of the main components for the correct reconstruction of the dynamic world. Historical approaches based on stereo vision and other 3D perception technologies (e.g. LIDAR) have been adapted to the ADAS first and autonomous ground vehicles, after, providing excellent results. The obstacles detection is a very broad field and this domain counts a lot of works in the last years. In academic research, it has been clearly established the essential role of these systems to realize active safety systems for accident prevention, reflecting also the innovative systems introduced by industry. These systems need to accurately assess situational criticalities and simultaneously assess awareness of these criticalities by the driver; it requires that the obstacles detection algorithms must be reliable and accurate, providing: a real-time output, a stable and robust representation of the environment and an estimation independent from lighting and weather conditions. Initial systems relied on only one exteroceptive sensor (e.g. radar or laser for ACC and camera for LDW) in addition to proprioceptive sensors such as wheel speed and yaw rate sensors. But, current systems, such as ACC operating at the entire speed range or autonomous braking for collision avoidance, require the use of multiple sensors since individually they can not meet these requirements. It has led the community to move towards the use of a combination of them in order to exploit the benefits of each one. Pedestrians and vehicles detection are ones of the major thrusts in situational criticalities assessment, still remaining an active area of research. ADASs are the most prominent use case of pedestrians and vehicles detection. Vehicles should be equipped with sensing capabilities able to detect and act on objects in dangerous situations, where the driver would not be able to avoid a collision. A full ADAS or autonomous vehicle, with regard to pedestrians and vehicles, would not only include detection but also tracking, orientation, intent analysis, and collision prediction. The system detects obstacles using a probabilistic occupancy grid built from a multi-resolution disparity map. Obstacles classification is based on an AdaBoost SoftCascade trained on Aggregate Channel Features. A final stage of tracking and fusion guarantees stability and robustness to the result.

Intelligent Computations for Flood Monitoring

Floods represent the most devastating natural hazards in the world, affecting more people and causing more property damage than any other natural phenomena. One of the important problems associated with flood monitoring is flood extent extraction from satellite imagery, since it is impractical to acquire the flood area through field observations. This paper presents a method to flood extent extraction from synthetic-aperture radar (SAR) images that is based on intelligent computations. In particular, we apply artificial neural networks, self-organizing Kohonen’s maps (SOMs), for SAR image segmentation and classification. We tested our approach to process data from three different satellite sensors: ERS-2/SAR (during flooding on Tisza river, Ukraine and Hungary, 2001), ENVISAT/ASAR WSM (Wide Swath Mode) and RADARSAT-1 (during flooding on Huaihe river, China, 2007). Obtained results showed the efficiency of our approach.

Projected sequential Gaussian processes:a C++ tool for interpolation of large datasets with heterogeneous noise

Heterogeneous datasets arise naturally in most applications due to the use of a variety of sensors and measuring platforms. Such datasets can be heterogeneous in terms of the error characteristics and sensor models. Treating such data is most naturally accomplished using a Bayesian or model-based geostatistical approach; however, such methods generally scale rather badly with the size of dataset, and require computationally expensive Monte Carlo based inference. Recently within the machine learning and spatial statistics communities many papers have explored the potential of reduced rank representations of the covariance matrix, often referred to as projected or fixed rank approaches. In such methods the covariance function of the posterior process is represented by a reduced rank approximation which is chosen such that there is minimal information loss. In this paper a sequential Bayesian framework for inference in such projected processes is presented. The observations are considered one at a time which avoids the need for high dimensional integrals typically required in a Bayesian approach. A C++ library, gptk, which is part of the INTAMAP web service, is introduced which implements projected, sequential estimation and adds several novel features. In particular the library includes the ability to use a generic observation operator, or sensor model, to permit data fusion. It is also possible to cope with a range of observation error characteristics, including non-Gaussian observation errors. Inference for the covariance parameters is explored, including the impact of the projected process approximation on likelihood profiles. We illustrate the projected sequential method in application to synthetic and real datasets. Limitations and extensions are discussed. © 2010 Elsevier Ltd.

Uma plataforma adaptável para localização em ambientes internos

Location systems have become increasingly part of people's lives. For outdoor environments, GPS appears as standard technology, widely disseminated and used. However, people usually spend most of their daily time in indoor environments, such as: hospitals, universities, factories, buildings, etc. In these environments, GPS does not work properly causing an inaccurate positioning. Currently, to perform the location of people or objects in indoor environments no single technology could reproduce for indoors the same result achieved by GPS for outdoors environments. Due to this, it is necessary to consider use of information from multiple sources using diferent technologies. Thus, this work aims to build an Adaptable Platform for Indoor location. Based on this goal, the IndoLoR platform is proposed. This platform aims to allow information reception from diferent sources, data processing, data fusion, data storage and data retrieval for the indoor location context.

Uma plataforma adaptável para localização em ambientes internos

Location systems have become increasingly part of people's lives. For outdoor environments, GPS appears as standard technology, widely disseminated and used. However, people usually spend most of their daily time in indoor environments, such as: hospitals, universities, factories, buildings, etc. In these environments, GPS does not work properly causing an inaccurate positioning. Currently, to perform the location of people or objects in indoor environments no single technology could reproduce for indoors the same result achieved by GPS for outdoors environments. Due to this, it is necessary to consider use of information from multiple sources using diferent technologies. Thus, this work aims to build an Adaptable Platform for Indoor location. Based on this goal, the IndoLoR platform is proposed. This platform aims to allow information reception from diferent sources, data processing, data fusion, data storage and data retrieval for the indoor location context.

Soil organic carbon storage and soil properties for 50 soil profiles in the Lena River Delta including land form description and map

To project the future development of the soil organic carbon (SOC) storage in permafrost environments, the spatial and vertical distribution of key soil properties and their landscape controls needs to be understood. This article reports findings from the Arctic Lena River Delta where we sampled 50 soil pedons. These were classified according to the U.S.D.A. Soil Taxonomy and fall mostly into the Gelisol soil order used for permafrost-affected soils. Soil profiles have been sampled for the active layer (mean depth 58±10 cm) and the upper permafrost to one meter depth. We analyze SOC stocks and key soil properties, i.e. C%, N%, C/N, bulk density, visible ice and water content. These are compared for different landscape groupings of pedons according to geomorphology, soil and land cover and for different vertical depth increments. High vertical resolution plots are used to understand soil development. These show that SOC storage can be highly variable with depth. We recommend the treatment of permafrost-affected soils according to subdivisions into: the surface organic layer, mineral subsoil in the active layer, organic enriched cryoturbated or buried horizons and the mineral subsoil in the permafrost. The major geomorphological units of a subregion of the Lena River Delta were mapped with a land form classification using a data-fusion approach of optical satellite imagery and digital elevation data to upscale SOC storage. Landscape mean SOC storage is estimated to 19.2±2.0 kg C/m**2. Our results show that the geomorphological setting explains more soil variability than soil taxonomy classes or vegetation cover. The soils from the oldest, Pleistocene aged, unit of the delta store the highest amount of SOC per m**2 followed by the Holocene river terrace. The Pleistocene terrace affected by thermal-degradation, the recent floodplain and bare alluvial sediments store considerably less SOC in descending order.